Assessing the validity of two indirect questioning techniques: A Stochastic Lie Detector versus the Crosswise Model

Hoffmann, Adrian; Musch, Jochen

doi:10.3758/s13428-015-0628-6

Cited by 42 publications

(57 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In line with this reasoning, the CWM has shown high levels of comprehensibility and subjectively perceived privacy protection in an experimental comparison of several indirect questioning techniques (Hoffmann et al, 2017). Moreover, the results from comparative validation studies (Hoffmann & Musch, 2016;Jann, Jerke, & Krumpal, 2012;Korndörfer, Krumpal, & Schmukle, 2014;Kundt, Misch, & Nerré, 2013;Nakhaee, Pakravan, & Nakhaee, 2013;Thielmann, Heck, & Hilbig, 2016; but see Höglinger, Jann, & Diekmann, 2016) and of one strong validation study with a known prevalence of the sensitive attribute (Hoffmann et al, 2015) suggest that the CWM outperforms competing approaches with respect to the control of social-desirability bias in sensitive surveys.…”

supporting

confidence: 57%

“…5A). Even though this sample size is rather small relative to the samples typically recruited in RR studies (e.g., Hoffmann & Musch, 2016;Schröter et al, 2016;Thielmann et al, 2016), the ECWM has a high power to detect 50% nonadherence of all participants, irrespective of the true prevalence. In contrast, the power depends on the true prevalence if only carriers or only noncarriers show nonadherence.…”

Section: Statistical Power Of the Ecwmmentioning

confidence: 98%

“…Furthermore, a substantial proportion of carriers were estimated to provide untruthful responses (see also Hilbig, Moshagen, & Zettler, 2015). In a recent comparative validation, however, the SLD overestimated the known prevalence of a nonsensitive control attribute (Hoffmann & Musch, 2016) suggesting that the inherent model assumption of all noncarriers adhering to the instructions might have been violated. Finally, a drawback of both CDM and SLD is their comparably low statistical efficiency (on top of the statistical inefficiency of all RR variants due to adding random noise to conceal the respondents' true status; Ulrich, Schröter, Striegel, & Simon, 2012), which results from the inclusion of the additional parameters that need to be estimated.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Detecting nonadherence without loss in efficiency: A simple extension of the crosswise model

2017

Self Cite

View full text Add to dashboard Cite

In surveys concerning sensitive behavior or attitudes, respondents often do not answer truthfully, because of social desirability bias. To elicit more honest responding, the randomized-response (RR) technique aims at increasing perceived and actual anonymity by prompting respondents to answer with a randomly modified and thus uninformative response. In the crosswise model, as a particularly promising variant of the RR, this is achieved by adding a second, nonsensitive question and by prompting respondents to answer both questions jointly. Despite increased privacy protection and empirically higher prevalence estimates of socially undesirable behaviors, evidence also suggests that some respondents might still not adhere to the instructions, in turn leading to questionable results. Herein we propose an extension of the crosswise model (ECWM) that makes it possible to detect several types of response biases with adequate power in realistic sample sizes. Importantly, the ECWM allows for testing the validity of the model's assumptions without any loss in statistical efficiency. Finally, we provide an empirical example supporting the usefulness of the ECWM.

show abstract

supporting

confidence: 57%

Section: Statistical Power Of the Ecwmmentioning

confidence: 98%

mentioning

confidence: 99%

See 1 more Smart Citation

Detecting nonadherence without loss in efficiency: A simple extension of the crosswise model

2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Future research can assess why individuals choose to research answers. Using a privacy preserving design (see, e.g., Hoffman and Musch, 2015) would allow researchers to ask respondents directly if they researched answers and, if they did, why did they choose to do so?…”

Section: Discussionmentioning

confidence: 99%

Exploring the difference in participants’ factual knowledge between online and in-person survey modes

Burnett

2016

Research & Politics

View full text Add to dashboard Cite

Over the past decade, an increasing number of scholars and professionals have turned to the Internet to gather samples of subjects for research ranging from public opinion surveys to experiments in the social sciences. While there has been a focus on whether online samples are representative and accurate, fewer studies examine the behavioral differences between individuals who participate in surveys and experiments on a computer versus in-person. Here, I use an experiment to gauge whether respondents who self-complete surveys online are more likely to register higher knowledge scores compared with respondents who self-complete surveys with pen and paper in a laboratory. The results show that subjects in the online group are significantly more likely to answer knowledge questions correctly across a range of topics. Patterns in the data imply respondents are researching some answers.

show abstract

“…For a comprehensive review of the topic, interested readers are referred to Fox and Tracy (), Chaudhuri and Mukerjee (), Chaudhuri (), Chaudhuri and Christofides (), Tian and Tang (). Useful and detailed studies on recent methodological advances, more complex estimation problems and new challenges may be found, among others, in Arcos, Rueda, and Singh (), Barabesi, Diana, and Perri (, ), Diana and Perri (), Fox, Entink, and Avetisyan (), Glynn (), Groenitz (), Hoffmann and Musch (), Hoffmann, Diedenhofen, Verschuere, and Musch (), Hussain, Shabbir, and Shabbir (), Ibrahim (), Imai (), Imai, Park, and Greene (), Liu and Tian (), Moshagen, Hilbig, Erdfelder, and Moritz (), Nepusz, Petróczi, Naughton, Epton, and Norman (), Perri and van der Heijden (), Petróczi et al. (), Rueda, Cobo, and Arcos (), Tsuchiya (), Ulrich, Schörter, Striegel, and Simon (), Wu and Tang ().…”

Section: Introductionmentioning

confidence: 99%

Multiple sensitive estimation and optimal sample size allocation in the item sum technique

2017

View full text Add to dashboard Cite

For surveys of sensitive issues in life sciences, statistical procedures can be used to reduce nonresponse and social desirability response bias. Both of these phenomena provoke nonsampling errors that are difficult to deal with and can seriously flaw the validity of the analyses. The item sum technique (IST) is a very recent indirect questioning method derived from the item count technique that seeks to procure more reliable responses on quantitative items than direct questioning while preserving respondents' anonymity. This article addresses two important questions concerning the IST: (i) its implementation when two or more sensitive variables are investigated and efficient estimates of their unknown population means are required; (ii) the determination of the optimal sample size to achieve minimum variance estimates. These aspects are of great relevance for survey practitioners engaged in sensitive research and, to the best of our knowledge, were not studied so far. In this article, theoretical results for multiple estimation and optimal allocation are obtained under a generic sampling design and then particularized to simple random sampling and stratified sampling designs. Theoretical considerations are integrated with a number of simulation studies based on data from two real surveys and conducted to ascertain the efficiency gain derived from optimal allocation in different situations. One of the surveys concerns cannabis consumption among university students. Our findings highlight some methodological advances that can be obtained in life sciences IST surveys when optimal allocation is achieved.

show abstract

Assessing the validity of two indirect questioning techniques: A Stochastic Lie Detector versus the Crosswise Model

Cited by 42 publications

References 89 publications

Detecting nonadherence without loss in efficiency: A simple extension of the crosswise model

Detecting nonadherence without loss in efficiency: A simple extension of the crosswise model

Exploring the difference in participants’ factual knowledge between online and in-person survey modes

Multiple sensitive estimation and optimal sample size allocation in the item sum technique

Contact Info

Product

Resources

About